© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 252880
    Prev
    Next
    INDEX
    Explanations

    programming code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    «
    0.50
     «
    0.49
    eyse
    0.44
     há
    0.41
     sol
    0.40
    פס
    0.39
    Ao
    0.38
     ú
    0.38
     ai
    0.38
     يح
    0.37
    POSITIVE LOGITS
     einer
    0.63
    Dieser
    0.63
     neue
    0.63
     deutsche
    0.63
     Hinweis
    0.60
     ziehen
    0.60
     zwischen
    0.60
     ihre
    0.59
     ihrer
    0.59
     Haupt
    0.59
    Activations Density 0.001%

    No Known Activations